COVID-19 Analysis
Katie Forthman
Tue May 19 10:13:33 2020
Click here for interactive plots:
Click here to see how cities and counties overlap:
Compare COVID stats to Neighborhood Factors
data.cor <- cor(county.Demo_and_Covid.allcounties[,-1], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
Compare COVID stats to 500 cities data and Neighborhood Factors
data.cor2 <- cor(county.Demo_and_Covid.500counties[,-c(1:2)], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor2, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
corrplot.mixed(data.cor2[7:13,c(1:5, 14:42,6)], upper = 'ellipse', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
—-Linear Mixed Effects Model —-
this.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)", data = county.Demo_and_Covid.500counties)## Warning: Some predictor variables are on very different scales: consider
## rescaling
## Warning: Some predictor variables are on very different scales: consider
## rescalingprint(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -1203.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.0674 -0.3056 -0.0687 0.2019 6.2770
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000001959 0.001400
## Residual 0.000012843 0.003584
## Number of obs: 178, groups: stateID, 33
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) -0.0123512126 0.0098299025 76.1935681199
## Affluence 0.0047917050 0.0011144008 112.3467540308
## Singletons.in.Tract 0.0007809158 0.0009022809 148.8040151883
## Seniors.in.Tract 0.0005689063 0.0011881947 154.8291844011
## African.Americans.in.Tract 0.0010174701 0.0009913028 155.5449895391
## Noncitizens.in.Tract 0.0010009696 0.0007684588 129.1588737368
## High.BP 0.0001957696 0.0001888297 120.6843513404
## Binge.Drinking 0.0001798986 0.0001623035 49.5852280689
## Cancer -0.0012724124 0.0011142254 113.2668658538
## Asthma 0.0008474238 0.0005733608 53.6697044247
## Heart.Disease 0.0017443244 0.0013218150 85.4300617400
## COPD -0.0003121978 0.0010998810 84.1694042879
## Smoking -0.0000308360 0.0002295060 90.7314416507
## Diabetes -0.0007022166 0.0005395354 89.6535073575
## No.Physical.Activity -0.0000720930 0.0002079870 98.6028384549
## Obesity 0.0002873328 0.0001777978 120.3554541997
## Poor.Sleeping.Habits -0.0000549025 0.0001653870 130.7718628417
## Poor.Mental.Health -0.0000842616 0.0004375961 35.0113973609
## Testing_Rate 0.0000006624 0.0000002758 44.2698134349
## Hospitalization_Rate -0.0000640894 0.0000962549 30.4993754427
## t value Pr(>|t|)
## (Intercept) -1.256 0.2128
## Affluence 4.300 0.0000366 ***
## Singletons.in.Tract 0.865 0.3882
## Seniors.in.Tract 0.479 0.6328
## African.Americans.in.Tract 1.026 0.3063
## Noncitizens.in.Tract 1.303 0.1950
## High.BP 1.037 0.3019
## Binge.Drinking 1.108 0.2730
## Cancer -1.142 0.2559
## Asthma 1.478 0.1453
## Heart.Disease 1.320 0.1905
## COPD -0.284 0.7772
## Smoking -0.134 0.8934
## Diabetes -1.302 0.1964
## No.Physical.Activity -0.347 0.7296
## Obesity 1.616 0.1087
## Poor.Sleeping.Habits -0.332 0.7404
## Poor.Mental.Health -0.193 0.8484
## Testing_Rate 2.402 0.0206 *
## Hospitalization_Rate -0.666 0.5105
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence 0.106
## Sngltns.n.T 0.029 0.071
## Snrs.n.Trct 0.545 0.387 0.197
## Afrcn.Am..T 0.146 0.156 -0.401 0.148
## Nnctzns.n.T -0.006 0.099 0.036 0.063 -0.086
## High.BP -0.021 0.244 0.057 0.107 -0.086 0.386
## Bing.Drnkng -0.308 -0.169 -0.291 -0.164 0.072 0.027 0.125
## Cancer -0.591 -0.184 0.180 -0.316 -0.071 -0.132 -0.362 -0.089
## Asthma -0.400 -0.201 -0.254 -0.215 0.086 0.092 0.164 0.003 0.071
## Heart.Dises -0.153 0.079 -0.301 -0.156 0.249 -0.107 -0.002 0.056 -0.471
## COPD 0.574 0.026 0.156 0.280 -0.023 0.276 0.155 0.087 -0.280
## Smoking -0.145 0.146 -0.177 -0.106 -0.049 0.016 -0.060 -0.303 0.076
## Diabetes 0.097 -0.351 -0.103 -0.219 -0.306 -0.308 -0.535 0.048 0.235
## N.Physcl.Ac -0.195 -0.032 0.082 -0.025 -0.032 -0.228 -0.088 0.121 0.472
## Obesity 0.001 0.416 0.434 0.302 0.135 0.189 -0.092 -0.225 0.104
## Pr.Slpng.Hb -0.441 -0.390 0.138 -0.352 -0.338 -0.034 -0.188 0.099 0.137
## Pr.Mntl.Hlt -0.352 0.267 -0.067 -0.045 0.098 -0.163 -0.052 0.091 0.330
## Testing_Rat 0.238 -0.078 0.009 0.036 0.022 -0.047 -0.031 -0.032 -0.218
## Hsptlztn_Rt -0.120 -0.235 -0.100 -0.232 -0.063 -0.072 -0.108 -0.143 0.023
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H Pr.M.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.275
## COPD -0.389 -0.561
## Smoking 0.087 0.210 -0.502
## Diabetes -0.122 -0.303 -0.078 0.222
## N.Physcl.Ac 0.018 -0.379 -0.015 -0.328 -0.081
## Obesity -0.264 -0.090 0.161 -0.200 -0.385 -0.060
## Pr.Slpng.Hb 0.073 0.246 -0.190 -0.030 -0.020 -0.105 -0.164
## Pr.Mntl.Hlt -0.225 0.085 -0.456 0.066 0.010 0.059 0.078 -0.167
## Testing_Rat -0.343 -0.029 0.220 0.140 0.116 -0.307 0.119 -0.146 -0.158
## Hsptlztn_Rt 0.103 0.105 -0.107 0.101 0.065 -0.053 -0.033 -0.015 -0.105
## Tstn_R
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises
## COPD
## Smoking
## Diabetes
## N.Physcl.Ac
## Obesity
## Pr.Slpng.Hb
## Pr.Mntl.Hlt
## Testing_Rat
## Hsptlztn_Rt 0.182
## fit warnings:
## Some predictor variables are on very different scales: consider rescalingthis.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + (1 | stateID)", data = county.Demo_and_Covid.500counties)
print(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -2465.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6790 -0.3724 -0.0739 0.2446 6.8638
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000007308 0.002703
## Residual 0.000011654 0.003414
## Number of obs: 326, groups: stateID, 51
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) -0.02140957 0.00771358 195.54186772 -2.776
## Affluence 0.00282174 0.00069812 303.08988393 4.042
## Singletons.in.Tract 0.00082282 0.00065092 300.54473214 1.264
## Seniors.in.Tract 0.00040801 0.00082234 304.28385289 0.496
## African.Americans.in.Tract 0.00166644 0.00079506 306.59642385 2.096
## Noncitizens.in.Tract 0.00171672 0.00064276 274.04468546 2.671
## High.BP -0.00002198 0.00014408 299.96234293 -0.153
## Binge.Drinking 0.00037583 0.00015200 162.83640155 2.473
## Cancer -0.00033234 0.00084602 268.87153157 -0.393
## Asthma 0.00064920 0.00050411 144.46523394 1.288
## Heart.Disease 0.00297286 0.00108691 215.47370255 2.735
## COPD -0.00117145 0.00082291 209.61703924 -1.424
## Smoking -0.00022335 0.00019001 254.92087021 -1.175
## Diabetes -0.00110155 0.00040702 271.74843821 -2.706
## No.Physical.Activity 0.00029776 0.00016362 241.29287072 1.820
## Obesity 0.00022866 0.00013214 307.89260848 1.731
## Poor.Sleeping.Habits 0.00025114 0.00012735 298.13961754 1.972
## Poor.Mental.Health -0.00013631 0.00042838 105.56662407 -0.318
## Pr(>|t|)
## (Intercept) 0.00605 **
## Affluence 0.0000673 ***
## Singletons.in.Tract 0.20718
## Seniors.in.Tract 0.62014
## African.Americans.in.Tract 0.03690 *
## Noncitizens.in.Tract 0.00802 **
## High.BP 0.87886
## Binge.Drinking 0.01444 *
## Cancer 0.69476
## Asthma 0.19987
## Heart.Disease 0.00675 **
## COPD 0.15607
## Smoking 0.24090
## Diabetes 0.00723 **
## No.Physical.Activity 0.07002 .
## Obesity 0.08454 .
## Poor.Sleeping.Habits 0.04953 *
## Poor.Mental.Health 0.75096
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence -0.054
## Sngltns.n.T -0.054 0.042
## Snrs.n.Trct 0.391 0.293 0.073
## Afrcn.Am..T 0.241 0.076 -0.404 0.202
## Nnctzns.n.T -0.072 0.153 0.125 0.058 -0.192
## High.BP -0.094 0.158 0.098 0.008 -0.232 0.325
## Bing.Drnkng -0.491 -0.037 -0.204 -0.067 0.041 -0.076 0.148
## Cancer -0.494 -0.095 0.231 -0.170 -0.074 -0.065 -0.330 -0.018
## Asthma -0.271 -0.094 -0.262 -0.122 -0.016 0.212 0.049 0.010 -0.156
## Heart.Dises -0.059 0.079 -0.302 -0.132 0.213 -0.055 0.002 0.034 -0.603
## COPD 0.479 0.007 0.130 0.171 -0.007 0.156 0.056 0.058 -0.211
## Smoking -0.041 0.105 -0.119 -0.138 -0.104 0.159 -0.082 -0.327 0.156
## Diabetes 0.036 -0.302 -0.077 -0.132 -0.230 -0.250 -0.447 0.074 0.369
## N.Physcl.Ac -0.117 0.035 0.102 0.079 0.059 -0.275 0.004 0.128 0.334
## Obesity -0.066 0.382 0.398 0.201 0.132 0.192 -0.103 -0.145 0.118
## Pr.Slpng.Hb -0.384 -0.349 0.162 -0.324 -0.320 -0.046 -0.156 0.087 0.028
## Pr.Mntl.Hlt -0.353 0.184 -0.009 0.025 0.053 -0.164 0.030 0.130 0.416
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.335
## COPD -0.321 -0.493
## Smoking 0.144 0.084 -0.475
## Diabetes -0.106 -0.435 -0.005 0.277
## N.Physcl.Ac -0.021 -0.359 0.088 -0.274 -0.168
## Obesity -0.124 -0.020 0.090 -0.220 -0.375 -0.044
## Pr.Slpng.Hb 0.001 0.239 -0.091 -0.170 -0.061 -0.152 -0.115
## Pr.Mntl.Hlt -0.438 -0.064 -0.390 -0.030 0.070 -0.088 0.024 -0.079Testing Rate
testing.data.state <- compiled.stats[[length(daily_filenames)]][, c("Province_State", "Testing_Rate")]
testing.data.state <- testing.data.state[!is.na(testing.data.state$Testing_Rate),]
testing.data.state <- testing.data.state[order(testing.data.state$Testing_Rate),]
col.state <- rep("pink", nrow(testing.data.state))
avg.test.rate <- mean(testing.data.state$Testing_Rate, na.rm = T)
col.state[testing.data.state$Testing_Rate < avg.test.rate] <- "grey"
col.state[testing.data.state$Province_State == "Oklahoma"] <- "lightblue"
par(mar = c(5,6,4,2))
barplot(testing.data.state$Testing_Rate, names.arg = testing.data.state$Province_State, horiz = T, main = "Testing Rate by State", las = 2, cex.axis = 1, cex.names = 0.5, col = col.state, border = F, xlab = "Total number of people tested per 100,000 persons.")
abline(v = avg.test.rate, col = "red")
text(x = avg.test.rate + 10, y = 1, labels = "Average Testing Rate", adj = c(0, 0.5), col = "red")
Pink highlights the last 14 days.
day.first.case <- min(which(US.total$cases.total > 100))
n.days <- nrow(US.total)
twoweek.col <- c(rep("grey", n.days-day.first.case-13), rep("pink", 14))
par(mar = c(5,5,4,2))
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$rise.cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Cases of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$rise.deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Deaths of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)